Publications (52)
Two-Timescale Resource Allocation for Cooperative D2D Communication: A Matching Game Approach
Yiling Yuan, Tao Yang, Yulin Hu +2
In this paper, we consider a cooperative device-todevice (D2D) communication system, where the D2D transmitters (DTs) act as relays to assist the densified cellular network users (…
Object Activity Scene Description, Construction and Recognition
Hui Feng, Shanshan Wang, Shuzhi Sam Ge
Action recognition is a critical task for social robots to meaningfully engage with their environment. 3D human skeleton-based action recognition is an attractive research area in…
OptHQC: Optimize HQC for High-Performance Post-Quantum Cryptography
Ben Dong, Hui Feng, Qian Wang
As post-quantum cryptography (PQC) becomes increasingly critical for securing future communication systems, the performance overhead introduced by quantum-resistant algorithms pres…
Matching Based Two-Timescale Resource Allocation for Cooperative D2D Communication
Yiling Yuan, Tao Yang, Yulin Hu +2
We consider a cooperative device-to-device (D2D) communication system, where the D2D transmitters (DTs) act as relays to assist cellular users (CUs) in exchange for the opportuniti…
Cross-Lingual Speech Emotion Recognition: Humans vs. Self-Supervised Models
Zhichen Han, Tianqi Geng, Hui Feng +3
Utilizing Self-Supervised Learning (SSL) models for Speech Emotion Recognition (SER) has proven effective, yet limited research has explored cross-lingual scenarios. This study pre…
Predicting Diabetic Macular Edema Treatment Responses Using OCT: Dataset and Methods of APTOS Competition
Weiyi Zhang, Peranut Chotcomwongse, Yinwen Li +15
Diabetic macular edema (DME) significantly contributes to visual impairment in diabetic patients. Treatment responses to intravitreal therapies vary, highlighting the need for pati…
Traffic-Aware Transmission Mode Selection in D2D-enabled Cellular Networks with Token System
Yiling Yuan, Tao Yang, Hui Feng +4
We consider a D2D-enabled cellular network where user equipments (UEs) owned by rational users are incentivized to form D2D pairs using tokens. They exchange tokens electronically…
Regularized Recovery by Multi-order Partial Hypergraph Total Variation
Ruyuan Qu, Jiaqi He, Hui Feng +2
Capturing complex high-order interactions among data is an important task in many scenarios. A common way to model high-order interactions is to use hypergraphs whose topology can…
SharpGAN: Receptive Field Block Net for Dynamic Scene Deblurring
Hui Feng, Jundong Guo, Sam Shuzhi Ge
When sailing at sea, the smart ship will inevitably produce swaying motion due to the action of wind, wave and current, which makes the image collected by the visual sensor appear…
Distilled Large Language Model in Confidential Computing Environment for System-on-Chip Design
Dong Ben, Hui Feng, Qian Wang
Large Language Models (LLMs) are increasingly used in circuit design tasks and have typically undergone multiple rounds of training. Both the trained models and their associated tr…
Effects of Tonal Coarticulation and Prosodic Positions on Tonal Contours of Low Rising Tones: In the Case of Xiamen Dialect
Yiying Hu, Hui Feng, Qinghua Zhao +1
Few studies have worked on the effects of tonal coarticulation and prosodic positions on the low rising tone in Xiamen Dialect. This study addressed such an issue. To do so, a new…
A Fast Transient Backend to Detect FRBs with the Tianlai Dish Pathfinder Array
Zijie Yu, Furen Deng, Shijie Sun +11
The Tianlai Dish Pathfinder array is a radio interferometer array consisting of 16 six meter dish antennas. The original digital backend integration time is at the seconds level, d…
Sampling Theory of Bandlimited Continuous-Time Graph Signals
Feng Ji, Hui Feng, Hang Sheng +1
A continuous-time graph signal can be viewed as a time series of graph signals. It generalizes both the classical continuous-time signal and ordinary graph signal. Therefore, such…
Recovery of Graph Signals from Sign Measurements
Wenwei Liu, Hui Feng, Kaixuan Wang +2
Sampling and interpolation have been extensively studied, in order to reconstruct or estimate the entire graph signal from the signal values on a subset of vertexes, of which most…
Toward Packet Routing with Fully-distributed Multi-agent Deep Reinforcement Learning
Xinyu You, Xuanjie Li, Yuedong Xu +3
Packet routing is one of the fundamental problems in computer networks in which a router determines the next-hop of each packet in the queue to get it as quickly as possible to its…
DEMO: Disentangled Motion Latent Flow Matching for Fine-Grained Controllable Talking Portrait Synthesis
Peiyin Chen, Zhuowei Yang, Hui Feng +2
Audio-driven talking-head generation has advanced rapidly with diffusion-based generative models, yet producing temporally coherent videos with fine-grained motion control remains…
Brain-inspired and Self-based Artificial Intelligence
Yi Zeng, Feifei Zhao, Yuxuan Zhao +17
The question "Can machines think?" and the Turing Test to assess whether machines could achieve human-level intelligence is one of the roots of AI. With the philosophical argument…
The Impact Analysis of Delays in Asynchronous Federated Learning with Data Heterogeneity for Edge Intelligence
Ziruo Hao, Zhenhua Cui, Tao Yang +3
Federated learning (FL) has provided a new methodology for coordinating a group of clients to train a machine learning model collaboratively, bringing an efficient paradigm in edge…
Active Anomaly Detection with Switching Cost
Fengfan Qin, Da Chen, Hui Feng +3
The problem of detecting a single anomalous process among multiple independent processes is considered. Under a constraint on the number of processes that can be probed simultaneou…
Microbiome-derived bile acids contribute to elevated antigenic response and bone erosion in rheumatoid arthritis
Xiuli Su, Xiaona Li, Yanqin Bian +15
Rheumatoid arthritis (RA) is a chronic, disabling and incurable autoimmune disease. It has been widely recognized that gut microbial dysbiosis is an important contributor to the pa…
Fast Color-guided Depth Denoising for RGB-D Images by Graph Filtering
Qiwei Huang, Ruikang Li, Zidong Jiang +4
Depth images captured by off-the-shelf RGB-D cameras suffer from much stronger noise than color images. In this paper, we propose a method to denoise the depth images in RGB-D imag…
On Critical Sampling of Time-Vertex Graph Signals
Junhao Yu, Xuan Xie, Hui Feng +1
Joint time-vertex graph signals are pervasive in real-world. This paper focuses on the fundamental problem of sampling and reconstruction of joint time-vertex graph signals. We pro…
OD-GCN: Object Detection Boosted by Knowledge GCN
Zheng Liu, Zidong Jiang, Wei Feng +1
Classical CNN based object detection methods only extract the objects' image features, but do not consider the high-level relationship among objects in context. In this article, th…
Active Sampling for Approximately Bandlimited Graph Signals
Sijie Lin, Xuan Xie, Hui Feng +1
This paper investigates the active sampling for estimation of approximately bandlimited graph signals. With the assistance of a graph filter, an approximately bandlimited graph sig…
Observation of multi-component atomic Schrödinger cat states of up to 20 qubits
Chao Song, Kai Xu, Hekang Li +13
We report on deterministic generation of 18-qubit genuinely entangled Greenberger-Horne-Zeilinger (GHZ) state and multi-component atomic Schrödinger cat states of up to 20 qubits…
OntologyRAG: Better and Faster Biomedical Code Mapping with Retrieval-Augmented Generation (RAG) Leveraging Ontology Knowledge Graphs and Large Language Models
Hui Feng, Yuntzu Yin, Emiliano Reynares +1
Biomedical ontologies, which comprehensively define concepts and relations for biomedical entities, are crucial for structuring and formalizing domain-specific information represen…
Inferring topologies via driving-based generalized synchronization of two-layer networks
Yingfei Wang, Xiaoqun Wu, Hui Feng +2
The interaction topology among the constituents of a complex network plays a crucial role in the network's evolutionary mechanisms and functional behaviors. However, some network t…
Clawdrain: Exploiting Tool-Calling Chains for Stealthy Token Exhaustion in OpenClaw Agents
Ben Dong, Hui Feng, Qian Wang
Modern generative agents such as OpenClaw - an open-source, self-hosted personal assistant with a community skill ecosystem, are gaining attention and are used pervasively. However…
Online Signed Sampling of Bandlimited Graph Signals
Wenwei Liu, Hui Feng, Feng Ji +1
The theory of sampling and recovery of bandlimited graph signals has been extensively studied. However, in many cases, the observation of a signal is quite coarse. For example, use…
Sampling of Correlated Bandlimited Continuous Signals by Joint Time-vertex Graph Fourier Transform
Zhongyi Ni, Feng Ji, Hang Sheng +2
When sampling multiple signals, the correlation between the signals can be exploited to reduce the overall number of samples. In this paper, we study the sampling theory of multipl…
Signed Graph Learning with Hidden Nodes
Rong Ye, Xue-Qin Jiang, Hui Feng +2
Signed graphs, which are characterized by both positive and negative edge weights, have recently attracted significant attention in the field of graph signal processing (GSP). Exis…
MemSeg: A semi-supervised method for image surface defect detection using differences and commonalities
Minghui Yang, Peng Wu, Jing Liu +1
Under the semi-supervised framework, we propose an end-to-end memory-based segmentation network (MemSeg) to detect surface defects on industrial products. Considering the small int…
A Modular and Scalable Simulator for Connected-UAVs Communication in 5G Networks
Yong Su, Yiyi Chen, Shenghong Yi +4
Cellular-connected UAV systems have enabled a wide range of low-altitude aerial services. However, these systems still face many challenges, such as frequent handovers and the inef…
Subset Random Sampling and Reconstruction of Finite Time-Vertex Graph Signals
Hang Sheng, Qinji Shu, Hui Feng +1
Finite time-vertex graph signals (FTVGS) provide an efficient representation for capturing spatio-temporal correlations across multiple data sources on irregular structures. Althou…
HISTORY: An Efficient and Robust Algorithm for Noisy 1-bit Compressed Sensing
Biao Sun, Hui Feng, Xinxin Xu
We consider the problem of sparse signal recovery from 1-bit measurements. Due to the noise present in the acquisition and transmission process, some quantized bits may be flipped…
Fine-grained visual recognition with salient feature detection
Hui Feng, Shanshan Wang, Shuzhi Sam Ge
Computer vision based fine-grained recognition has received great attention in recent years. Existing works focus on discriminative part localization and feature learning. In this…
Subset Random Sampling of Finite Time-vertex Graph Signals
Hang Sheng, Qinji Shu, Hui Feng +1
Time-varying data with irregular structures can be described by finite time-vertex graph signals (FTVGS), which represent potential temporal and spatial relationships among multipl…
Sampling Theory of Jointly Bandlimited Time-vertex Graph Signals
Hang Sheng, Hui Feng, Junhao Yu +2
Time-vertex graph signal (TVGS) models describe time-varying data with irregular structures. The bandlimitedness in the joint time-vertex Fourier spectral domain reflects smoothnes…
Modeling QoE of Video Streaming in Wireless Networks with Large-Scale Measurement of User Behavior
Yuedong Xu, Zhujun Xiao, Hui Feng +3
Unraveling quality of experience (QoE) of video streaming is very challenging in bandwidth shared wireless networks. It is unclear how QoE metrics such as starvation probability an…
On Sampling of Multiple Correlated Stochastic Signals
Lin Jin, Hang Sheng, Hui Feng +1
Multiple stochastic signals possess inherent statistical correlations, yet conventional sampling methods that process each channel independently result in data redundancy. To lever…
Bayesian Design of Sampling Set for Bandlimited Graph Signals
Xuan Xie, Junhao Yu, Hui Feng +1
The design of sampling set (DoS) for bandlimited graph signals (GS) has been extensively studied in recent years, but few of them exploit the benefits of the stochastic prior of GS…
Inland Waterway Object Detection in Multi-environment: Dataset and Approach
Shanshan Wang, Haixiang Xu, Hui Feng +4
The success of deep learning in intelligent ship visual perception relies heavily on rich image data. However, dedicated datasets for inland waterway vessels remain scarce, limitin…
Exploiting Timing Side-Channels in Quantum Circuits Simulation Via ML-Based Methods
Ben Dong, Hui Feng, Qian Wang
As quantum computing advances, quantum circuit simulators serve as critical tools to bridge the current gap caused by limited quantum hardware availability. These simulators are ty…
A Cascaded Channel-Power Allocation for D2D Underlaid Cellular Networks Using Matching Theory
Yiling Yuan, Tao Yang, Yuedong Xu +2
We consider a device-to-device (D2D) underlaid cellular network, where each cellular channel can be shared by several D2D pairs and only one channel can be allocated to each D2D pa…
Building Altruistic and Moral AI Agent with Brain-inspired Emotional Empathy Mechanisms
Feifei Zhao, Hui Feng, Haibo Tong +5
As AI closely interacts with human society, it is crucial to ensure that its behavior is safe, altruistic, and aligned with human ethical and moral values. However, existing resear…
Learning for Matching Game in Cooperative D2D Communication with Incomplete Information
Yiling Yuan, Tao Yang, Hui Feng +1
This paper considers a cooperative device-to-device (D2D) communication system, where the D2D transmitters (DTs) act as relays to assist cellular users (CUs) in exchange for the op…
Invariant Federated Learning for Edge Intelligence: Mitigating Heterogeneity and Asynchrony via Exit Strategy and Invariant Penalty
Ziruo Hao, Zhenhua Cui, Tao Yang +3
This paper provides an invariant federated learning system for resource-constrained edge intelligence. This framework can mitigate the impact of heterogeneity and asynchrony via ex…
RGB-T Tracking via Multi-Modal Mutual Prompt Learning
Yang Luo, Xiqing Guo, Hui Feng +1
Object tracking based on the fusion of visible and thermal im-ages, known as RGB-T tracking, has gained increasing atten-tion from researchers in recent years. How to achieve a mor…
Sampling Policy Design for Tracking Time-Varying Graph Signals with Adaptive Budget Allocation
Xuan Xie, Hui Feng, Bo Hu
There have been many works that focus on the sampling set design for a static graph signal, but few for time-varying graph signals (GS). In this paper, we concentrate on how to sel…
Design of Sampling Set for Bandlimited Graph Signal Estimation
Xuan Xie, Hui Feng, Junlian Jia +1
It is of particular interest to reconstruct or estimate bandlimited graph signals, which are smoothly varying signals defined over graphs, from partial noisy measurements. However,…
The Transferability of Downsamped Sparse Graph Convolutional Networks
Qinji Shu, Hang Sheng, Feng Ji +2
To accelerate the training of graph convolutional networks (GCNs) on real-world large-scale sparse graphs, downsampling methods are commonly employed as a preprocessing step. Howev…
Robust Beamforming for Downlink 3D-MIMO Systems with -norm Bounded CSI Uncertainty
Kai Liu, Hui Feng, Tao Yang +1
In this paper, a novel robust beamforming scheme is proposed in three dimensional multi-input multi-output (3D-MIMO) systems. As one of the typical deployments of massive MIMO, a 3…